arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.18052cs.CV
收藏

高效3D内容重建与生成

Efficient 3D Content Reconstruction and Generation

TOYOTA TECHNOLOGICAL INSTITUTE AT CHICAGO(丰田技术研究所芝加哥分校)

Jiahao Li

AI总结:

本文提出了一种高效的3D内容生成和重建方法,通过结合多视图扩散和稀疏视图3D重建,实现了高质量的3D资产生成,并开发了FastMap算法以提高3D重建的速度和精度。

摘要:

自动3D内容创建旨在用能够从文本或图像直接合成或恢复3D资产的系统取代劳动密集型的建模和扫描流程。其应用范围涵盖视频游戏、虚拟现实、机器人技术和模拟,使资产原型设计、多样化的交互世界生成和高效的3D数据收集成为可能。当前解决方案主要遵循两种互补的范式:(i)文本或图像到3D生成,学习3D几何和外观的先验知识,以从自然语言或单视图图像创建新资产;(ii)3D重建,从RGB图像估计相机姿态和几何结构。本论文在两个方向上都取得了进展。在生成方面,我介绍了Instant3D,它结合了多视图扩散和前馈稀疏视图3D重建,可在5-20秒内生成高质量的资产。在重建方面,我开发了FastMap,一种结构从运动流水线,通过使用一阶优化与广泛融合的GPU内核,实现了比现有最先进方法快10倍的速度提升,同时保持了可比的姿态精度和下游新视图合成质量。

英文摘要:

Automatic 3D content creation seeks to replace labor-intensive modeling and scanning pipelines with systems that can synthesize or recover 3D assets directly from text or images. Its applications span video games, virtual reality, robotics, and simulation, enabling rapid asset prototyping, diverse interactive world generation, and efficient 3D data collection for training foundation models. Contemporary solutions largely follow two complementary paradigms: (i) text- or image-to-3D generation, which learns priors over 3D geometry and appearance to create novel assets from natural language or a single view image; and (ii) 3D reconstruction, which estimates camera poses and geometry from RGB images. This thesis advances both directions. On the generation side, I introduce Instant3D, which combines multi-view diffusion with feed-forward sparse-view 3D reconstruction to produce high-quality assets in 5-20 seconds. On the reconstruction side, I develop FastMap, a structure-from-motion pipeline that achieves up to 10x speedup over prior state-of-the-art by using first-order optimization with fused GPU kernels extensively, while maintaining comparable pose accuracy and downstream novel view synthesis quality.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑